deepseek-ai / deepseek-ai/DeepEP

Why NUM_MAX_NVL_PEERS must be 8?

Open
#50 5 comments 0 reactions 0 assignees View on GitHub
Dominant language
Cuda
Stars
10.1k
Forks
1.4k
Avg merge
2d 17h
Merged PRs (30d)
3

Description

In deep_ep.hpp, Can it be a smaller number? For example I only have a node with 2 H800 to run test_low_latency.py

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reading NUM_MAX_NVL_PEERS in deep_ep.hpp and then run test_low_latency.py on the stated two-H800 setup. Determine whether the peer limit can be smaller for that configuration; done means the low-latency test runs successfully with the reduced value, if supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python
Domain
distributed-systems
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.